Trying to use OCR to scan an image, it half works!

Hey friends
I’m trying to extract text from an image using Google Cloud Vision and it’s half working.
He gives me the first half of the document correctly and in a column structure, but then it starts to go wrong and he can’t seem to understand the whole picture properly.

Do you know a way to extract text from an image accurately?
I also tried to compare the received text and ask the GPT to compare the information to the image for me, but it doesn’t work at all and it makes up data for me that doesn’t really appear in the image.

You forgot to show us how does your original image look like, so we can’t tell what is wrong with the output as shown in your screenshot.

1 Like